velocity-agent-skills

Use when the user wants an agent to autonomously build, fix, or improve web-app software end-to-end with the strongest reasonable development, staging, verification, review-artifact, and handoff loop. Trigger on requests like "use /vl-cook", "cook", "run with this", "just build it", "iterate on this", "take it as far as you can", or long-running feature work where stopping after the first patch would be insufficient. Consider vl-stage, vl-screenshot, and vl-handoff when they help prove or package the work.

Use when current work needs to be handed off to another developer, agent, reviewer, manager, client, stakeholder, or team. Produces a context-rich handoff tailored to the recipient and delivery medium, including current status, decisions, changed files, verification, open risks, artifacts, and recommended next steps. Trigger on requests like "handoff", "write this up for", "brief the next person", "summarize progress for Slack", "prepare a review handoff", or "pass this to another agent".

Use when frontend work needs a shareable folder of screenshots for design, product, QA, stakeholder, or non-technical team review. Captures a whole feature flow across states/pages, creates a two-column clickable index.html contact sheet, and documents how to refresh the folder after UI changes. Works for any web project with a browser-accessible local or remote URL.

Use when a branch, worktree, local app, or cloud-agent task needs a staged test environment without disturbing the main checkout, especially for browser-facing web app work. Helps agents choose and set up the right strategy for browser/app testing across JavaScript/TypeScript, Python, PHP, Docker Compose, local framework servers, cloud sandboxes, and other project runtimes. Covers worktree placement, dev servers, ports, environment isolation, database/cache/queue isolation, verification URLs, logs, artifacts, and safe teardown.